AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Hearing Without Noticing? Attention-Aware Stealthy Black-Box Adversarial Audio Attacks

Tianyi Xu, Cheng'an Wei, Yue Zhao, Kai Chen

ICML 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add masking-aligned carrier selection (ablation)Ours · Physical attack ablationTalking rate: 70.00% -> 10.37%Improved
add masking-aligned carrier selection (ablation)Ours · Physical attack ablationSNR (dB): 14.81 -> 16.12Improved
add masking-aligned carrier selection (ablation)Ours · Physical attack ablationNormal rate: 7.85% -> 55.57%Improved
add attention-dilution loss instead of magnitude constraint (ablation)Ours · Physical attack ablationNormal rate: 9.28% -> 55.57%Improved
add attention-dilution loss instead of magnitude constraint (ablation)Ours · Physical attack ablationSNR (dB): 11.85 -> 16.12Improved
use Log Mel feature instead of MFCC (ablation)Ours · Physical attack ablationNormal rate: 35.73% -> 55.57%Improved
use Log Mel feature instead of MFCC (ablation)Ours · Physical attack ablationSNR (dB): 9.84 -> 16.12Improved
use man with low voice targetOurs · Voice type (Whisper)Normal rate: 55.57% -> 36.40%Hurt
use woman with happy voice targetOurs · Voice type (Whisper)Normal rate: 55.57% -> 77.30%Improved
use human recordings as targetOurs · Voice type (Whisper)Normal rate: 55.57% -> 50.00%Hurt
Ours vs Kenku on stealthy samples under defensesOurs · Defense: filteringattack success rate: 7.69% -> 30.78%Improved
Ours vs Kenku on perceptible samples under defensesOurs · Defense: filteringattack success rate: 61.54% -> 3.85%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy